--- layout: default title: Connectors has_children: false has_toc: false nav_order: 61 parent: Connecting to externally hosted models grand_parent: Integrating ML models redirect_from: - /ml-commons-plugin/extensibility/connectors/ --- # Creating connectors for third-party ML platforms **Introduced 2.9** {: .label .label-purple } Connectors facilitate access to models hosted on third-party machine learning (ML) platforms. OpenSearch provides connectors for several platforms, for example: - [Amazon SageMaker](https://aws.amazon.com/sagemaker/) allows you to host and manage the lifecycle of text embedding models, powering semantic search queries in OpenSearch. When connected, Amazon SageMaker hosts your models and OpenSearch is used to query inferences. This benefits Amazon SageMaker users who value its functionality, such as model monitoring, serverless hosting, and workflow automation for continuous training and deployment. - [OpenAI ChatGPT](https://openai.com/blog/chatgpt) enables you to invoke an OpenAI chat model from inside an OpenSearch cluster. - [Cohere](https://cohere.com/) allows you to use data from OpenSearch to power the Cohere large language models. - [Amazon Bedrock](https://aws.amazon.com/bedrock/) supports models like [Bedrock Titan Embeddings](https://aws.amazon.com/bedrock/titan/), which can drive semantic search and retrieval-augmented generation in OpenSearch. ## Connector blueprints A _connector blueprint_ defines the set of parameters (the request body) you need to provide when sending an API request to create a specific connector. Connector blueprints may differ based on the platform and the model that you are accessing. OpenSearch provides connector blueprints for several ML platforms and models. For a full list of connector blueprints provided by OpenSearch, see [Supported connectors](#supported-connectors). As an ML developer, you can also create connector blueprints for other platforms and models. Data scientists and administrators can then use the blueprint to create connectors. They are only required to enter their `credential` settings, such as `openAI_key`, for the service to which they are connecting. For information about creating connector blueprints, including descriptions of all parameters, see [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/remote-models/blueprints/). ## Supported connectors The following table lists all connector blueprints provided by OpenSearch. Follow the links to each connector blueprint for an example request that you can use to create the connector, including all parameters, and an example Predict API request. Platform | Model | Connector blueprint :--- | :--- | :--- [Amazon Bedrock](https://aws.amazon.com/bedrock/) | [AI21 Labs Jurassic-2 Mid](https://aws.amazon.com/bedrock/jurassic/) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/bedrock_connector_ai21labs_jurassic_blueprint.md) [Amazon Bedrock](https://aws.amazon.com/bedrock/) | [Anthropic Claude v2](https://aws.amazon.com/bedrock/claude/) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/bedrock_connector_anthropic_claude_blueprint.md) [Amazon Bedrock](https://aws.amazon.com/bedrock/) | [Titan Text Embeddings](https://aws.amazon.com/bedrock/titan/) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/bedrock_connector_titan_embedding_blueprint.md) [Amazon SageMaker](https://aws.amazon.com/sagemaker/) | Text embedding models | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/sagemaker_connector_blueprint.md) [Cohere](https://cohere.com/) | [Text Embedding models](https://docs.cohere.com/reference/embed) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/cohere_connector_embedding_blueprint.md) [Cohere](https://cohere.com/) | [Chat models](https://docs.cohere.com/reference/chat) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/main/docs/remote_inference_blueprints/cohere_connector_chat_blueprint.md) [OpenAI](https://openai.com/) | Chat models (for example, `gpt-3.5-turbo`) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/open_ai_connector_chat_blueprint.md) [OpenAI](https://openai.com/) | Completion models (for example, `text-davinci-003`) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/open_ai_connector_completion_blueprint.md) [OpenAI](https://openai.com/) | Text embedding models (for example, `text-embedding-ada-002`) | [Blueprint](https://github.com/opensearch-project/ml-commons/blob/2.x/docs/remote_inference_blueprints/openai_connector_embedding_blueprint.md) ## Creating a connector You can provision connectors in two ways: 1. [Create a standalone connector](#creating-a-standalone-connector): A standalone connector can be reused and shared by multiple models but requires access to both the model and connector in OpenSearch and the third-party platform, such as OpenAI or Amazon SageMaker, that the connector is accessing. Standalone connectors are saved in a connector index. 2. [Create a connector for a specific externally hosted model](#creating-a-connector-for-a-specific-model): Alternatively, you can create a connector that can only be used with the model for which it was created. To access such a connector, you only need access to the model itself because the connection is established inside the model. These connectors are saved in the model index. ## Creating a standalone connector Standalone connectors can be used by multiple models. To create a standalone connector, send a request to the `connectors/_create` endpoint and provide all of the parameters described in [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/remote-models/blueprints/): ```json POST /_plugins/_ml/connectors/_create { "name": "OpenAI Chat Connector", "description": "The connector to public OpenAI model service for GPT 3.5", "version": 1, "protocol": "http", "parameters": { "endpoint": "api.openai.com", "model": "gpt-3.5-turbo" }, "credential": { "openAI_key": "..." }, "actions": [ { "action_type": "predict", "method": "POST", "url": "https://${parameters.endpoint}/v1/chat/completions", "headers": { "Authorization": "Bearer ${credential.openAI_key}" }, "request_body": "{ \"model\": \"${parameters.model}\", \"messages\": ${parameters.messages} }" } ] } ``` {% include copy-curl.html %} ## Creating a connector for a specific model To create a connector for a specific model, provide all of the parameters described in [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/remote-models/blueprints/) within the `connector` object of a request to the `models/_register` endpoint: ```json POST /_plugins/_ml/models/_register { "name": "openAI-GPT-3.5 model with a connector", "function_name": "remote", "model_group_id": "lEFGL4kB4ubqQRzegPo2", "description": "test model", "connector": { "name": "OpenAI Connector", "description": "The connector to public OpenAI model service for GPT 3.5", "version": 1, "protocol": "http", "parameters": { "endpoint": "api.openai.com", "max_tokens": 7, "temperature": 0, "model": "text-davinci-003" }, "credential": { "openAI_key": "..." }, "actions": [ { "action_type": "predict", "method": "POST", "url": "https://${parameters.endpoint}/v1/completions", "headers": { "Authorization": "Bearer ${credential.openAI_key}" }, "request_body": "{ \"model\": \"${parameters.model}\", \"prompt\": \"${parameters.prompt}\", \"max_tokens\": ${parameters.max_tokens}, \"temperature\": ${parameters.temperature} }" } ] } } ``` {% include copy-curl.html %} ## Connector examples The following sections contain examples of connectors for popular ML platforms. For a full list of supported connectors, see [Supported connectors](#supported-connectors). ### OpenAI chat connector You can use the following example request to create a standalone OpenAI chat connector: ```json POST /_plugins/_ml/connectors/_create { "name": "OpenAI Chat Connector", "description": "The connector to public OpenAI model service for GPT 3.5", "version": 1, "protocol": "http", "parameters": { "endpoint": "api.openai.com", "model": "gpt-3.5-turbo" }, "credential": { "openAI_key": "..." }, "actions": [ { "action_type": "predict", "method": "POST", "url": "https://${parameters.endpoint}/v1/chat/completions", "headers": { "Authorization": "Bearer ${credential.openAI_key}" }, "request_body": "{ \"model\": \"${parameters.model}\", \"messages\": ${parameters.messages} }" } ] } ``` {% include copy-curl.html %} ### Amazon SageMaker connector You can use the following example request to create a standalone Amazon SageMaker connector: ```json POST /_plugins/_ml/connectors/_create { "name": "sagemaker: embedding", "description": "Test connector for Sagemaker embedding model", "version": 1, "protocol": "aws_sigv4", "credential": { "access_key": "...", "secret_key": "...", "session_token": "..." }, "parameters": { "region": "us-west-2", "service_name": "sagemaker" }, "actions": [ { "action_type": "predict", "method": "POST", "headers": { "content-type": "application/json" }, "url": "https://runtime.sagemaker.${parameters.region}.amazonaws.com/endpoints/lmi-model-2023-06-24-01-35-32-275/invocations", "request_body": "[\"${parameters.inputs}\"]" } ] } ``` {% include copy-curl.html %} The `credential` parameter contains the following options reserved for `aws_sigv4` authentication: - `access_key`: Required. Provides the access key for the AWS instance. - `secret_key`: Required. Provides the secret key for the AWS instance. - `session_token`: Optional. Provides a temporary set of credentials for the AWS instance. The `parameters` section requires the following options when using `aws_sigv4` authentication: - `region`: The AWS Region in which the AWS instance is located. - `service_name`: The name of the AWS service for the connector. ### Cohere connector You can use the following example request to create a standalone Cohere connector: ```json POST /_plugins/_ml/connectors/_create { "name": "", "description": "", "version": "", "protocol": "http", "credential": { "cohere_key": "" }, "parameters": { "model": "embed-english-v2.0", "truncate": "END" }, "actions": [ { "action_type": "predict", "method": "POST", "url": "https://api.cohere.ai/v1/embed", "headers": { "Authorization": "Bearer ${credential.cohere_key}" }, "request_body": "{ \"texts\": ${parameters.texts}, \"truncate\": \"${parameters.truncate}\", \"model\": \"${parameters.model}\" }", "pre_process_function": "connector.pre_process.cohere.embedding", "post_process_function": "connector.post_process.cohere.embedding" } ] } ``` {% include copy-curl.html %} ### Amazon Bedrock connector You can use the following example request to create a standalone Amazon Bedrock connector: ```json POST /_plugins/_ml/connectors/_create { "name": "Amazon Bedrock Connector: embedding", "description": "The connector to the Bedrock Titan embedding model", "version": 1, "protocol": "aws_sigv4", "parameters": { "region": "", "service_name": "bedrock" }, "credential": { "access_key": "", "secret_key": "", "session_token": "" }, "actions": [ { "action_type": "predict", "method": "POST", "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/amazon.titan-embed-text-v1/invoke", "headers": { "content-type": "application/json", "x-amz-content-sha256": "required" }, "request_body": "{ \"inputText\": \"${parameters.inputText}\" }", "pre_process_function": "\n StringBuilder builder = new StringBuilder();\n builder.append(\"\\\"\");\n String first = params.text_docs[0];\n builder.append(first);\n builder.append(\"\\\"\");\n def parameters = \"{\" +\"\\\"inputText\\\":\" + builder + \"}\";\n return \"{\" +\"\\\"parameters\\\":\" + parameters + \"}\";", "post_process_function": "\n def name = \"sentence_embedding\";\n def dataType = \"FLOAT32\";\n if (params.embedding == null || params.embedding.length == 0) {\n return params.message;\n }\n def shape = [params.embedding.length];\n def json = \"{\" +\n \"\\\"name\\\":\\\"\" + name + \"\\\",\" +\n \"\\\"data_type\\\":\\\"\" + dataType + \"\\\",\" +\n \"\\\"shape\\\":\" + shape + \",\" +\n \"\\\"data\\\":\" + params.embedding +\n \"}\";\n return json;\n " } ] } ``` {% include copy-curl.html %} ## Updating connector credentials In some cases, you may need to update credentials, like `access_key`, that you use to connect to externally hosted models. You can update credentials without undeploying the model by providing the new credentials in the following request: ```json PUT /_plugins/_ml/models/ { "connector": { "credential": { "openAI_key": "YOUR NEW OPENAI KEY" } } } ``` ## Next steps - To learn more about connecting to external models, see [Connecting to externally hosted models]({{site.url}}{{site.baseurl}}/ml-commons-plugin/remote-models/index/). - To learn more about model access control and model groups, see [Model access control]({{site.url}}{{site.baseurl}}/ml-commons-plugin/model-access-control/).